On Thu, May 19, 2022 at 6:35 PM Eric DeVolder <eric.devol...@oracle.com> wrote: > > > > On 5/13/22 09:10, Ani Sinha wrote: > > At any step when any validation fail in check_erst_backend_storage(), there > > is > > no need to continue further through other validation checks. Further, by > > continuing even when record_size is 0, we run the risk of triggering a > > divide > > by zero error if we continued with other validation checks. Hence, we should > > simply return from this function upon validation failure. > > > > CC: Peter Maydell <peter.mayd...@linaro.org> > > CC: Eric DeVolder <eric.devol...@oracle.com> > > Signed-off-by: Ani Sinha <a...@anisinha.ca> > > Reviewed-by: Eric DeVolder <eric.devol...@oracle.com>
Michael: Did you forget to queue this for your latest pull request? > > My apologies, I've been away for the past week. > Thank you for taking the time to correct this issue! > eric > > > --- > > hw/acpi/erst.c | 3 +++ > > 1 file changed, 3 insertions(+) > > > > diff --git a/hw/acpi/erst.c b/hw/acpi/erst.c > > index de509c2b48..df856b2669 100644 > > --- a/hw/acpi/erst.c > > +++ b/hw/acpi/erst.c > > @@ -440,6 +440,7 @@ static void check_erst_backend_storage(ERSTDeviceState > > *s, Error **errp) > > (record_size >= 4096) /* PAGE_SIZE */ > > )) { > > error_setg(errp, "ERST record_size %u is invalid", record_size); > > + return; > > } > > > > /* Validity check header */ > > @@ -450,6 +451,7 @@ static void check_erst_backend_storage(ERSTDeviceState > > *s, Error **errp) > > (le16_to_cpu(header->reserved) == 0) > > )) { > > error_setg(errp, "ERST backend storage header is invalid"); > > + return; > > } > > > > /* Check storage_size against record_size */ > > @@ -457,6 +459,7 @@ static void check_erst_backend_storage(ERSTDeviceState > > *s, Error **errp) > > (record_size > s->storage_size)) { > > error_setg(errp, "ACPI ERST requires storage size be multiple of " > > "record size (%uKiB)", record_size); > > + return; > > } > > > > /* Compute offset of first and last record storage slot */ > >